Browse > Computer Vision > Semantic Segmentation

Semantic Segmentation

754 papers with code · Computer Vision

Semantic segmentation, or image segmentation, is the task of clustering parts of an image together which belong to the same object class. It is a form of pixel-level prediction because each pixel in an image is classified according to a category.

Some example benchmarks for this task are Cityscapes, PASCAL VOC and ADE20K. Models are usually evaluated with the Mean Intersection-Over-Union (Mean IoU) and Pixel Accuracy metrics.

( Image credit: CSAILVision )

Leaderboards

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers with code

SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation

21 Jan 2020sunjesse/shape-attentive-unet

Despite the progress of deep learning in medical image segmentation, standard CNNs are still not fully adopted in clinical settings as they lack robustness and interpretability.

MEDICAL IMAGE SEGMENTATION SEMANTIC SEGMENTATION

7
21 Jan 2020

See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks

CVPR 2019 carrierlxk/COSNet

We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view.

SEMANTIC SEGMENTATION UNSUPERVISED VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION

135
19 Jan 2020

Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks

ICCV 2019 carrierlxk/AGNN

Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation.

SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION

79
19 Jan 2020

GridMask Data Augmentation

13 Jan 2020akuxcw/GridMask

Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective.

DATA AUGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

35
13 Jan 2020

Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

8 Jan 2020JaminFong/FNA

In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH OBJECT DETECTION SEMANTIC SEGMENTATION

37
08 Jan 2020

A context based deep learning approach for unbalanced medical image segmentation

8 Jan 2020Bala93/Context-aware-segmentation

Foreground-background class imbalance is a common occurrence in medical images, and U-Net has difficulty in handling class imbalance because of its cross entropy (CE) objective function.

MEDICAL IMAGE SEGMENTATION SEMANTIC SEGMENTATION

0
08 Jan 2020

Deep Snake for Real-Time Instance Segmentation

6 Jan 2020zju3dv/snake

This paper introduces a novel contour-based approach named deep snake for real-time instance segmentation.

OBJECT LOCALIZATION REAL-TIME INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

136
06 Jan 2020

Unpaired Multi-modal Segmentation via Knowledge Distillation

6 Jan 2020carrenD/ummkd

We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy.

SEMANTIC SEGMENTATION

27
06 Jan 2020

Visual Semantic SLAM with Landmarks for Large-Scale Outdoor Environment

4 Jan 20201989Ryan/Semantic_SLAM

Semantic SLAM is an important field in autonomous driving and intelligent agents, which can enable robots to achieve high-level navigation tasks, obtain simple cognition or reasoning ability and achieve language-based human-robot-interaction.

AUTONOMOUS DRIVING SEMANTIC SEGMENTATION

62
04 Jan 2020

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

2 Jan 2020aim-uofa/adet

The proposed BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer, thus being fast in inference.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

26
02 Jan 2020